Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3381 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2163. Min Act: -0.0000

Data Index: 954918 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2010. Min Act: -0.0000

Data Index: 754059 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2041. Min Act: -0.0000

Data Index: 875804 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1013451 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1852. Min Act: -0.0000

Data Index: 35526 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1784. Min Act: -0.0000

Data Index: 417154 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1719. Min Act: -0.0000

Data Index: 723539 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1661. Min Act: -0.0000

Data Index: 121940 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1214828 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1289633 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1309327 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1060864 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1335947 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1704. Min Act: -0.0000

Data Index: 405874 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1584. Min Act: -0.0000

Data Index: 504247 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1633. Min Act: -0.0000

Data Index: 144982 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1714. Min Act: -0.0000

Data Index: 837384 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1614. Min Act: -0.0000

Data Index: 7730 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1566. Min Act: -0.0000

Data Index: 156314 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1721. Min Act: -0.0000

Data Index: 397887 (C4 (Web Text))

Max Activating Token Index: 587